Chronicles-OCR - Mature Script Classification: leaderboard
Metric: Accuracy (%) of classifying the image into one of the Seven Chinese Scripts, on images of the mature scripts (Clerical, Regular, Running and Cursive), the paper Average column over the per-script results; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 29 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2.5 (Non-reasoning) | 77 |
| 2 | Seed 2.0 Pro (Non-reasoning) | 76.1 |
| 3 | Seed 2.0 Pro | 75.3 |
| 4 | Gemini 3.1 Pro (Preview) | 73.1 |
| 5 | Kimi K2.5 | 72.3 |
| 6 | Qwen 3.5 397B A17B (Non-reasoning) | 72.2 |
| 7 | Seed 1.8 | 71.1 |
| 8 | Qwen 3.5 35B A3B (Non-reasoning) | 68.1 |
| 9 | Claude Opus 4.7 (Thinking) | 66.8 |
| 10 | Qwen 3 VL 235B A22B Instruct | 64.9 |
| 11 | MiMo-V2-Omni | 62.3 |
| 12 | GPT-5 | 62.1 |
| 13 | Qwen 3 VL 8B Instruct | 60.9 |
| 14 | Qwen 3 VL 235B A22B (Thinking) | 60.4 |
| 15 | Qwen 2.5 VL 72B Instruct | 57.2 |
Interactive version: theaggregate.ai/benchmark?slug=chronicles-ocr-mature-script-classification · How It Works · Data refreshed daily, snapshot 2026-10-07.